think

Solid

Turns rough ideas into approved plans with validated structure before writing code. Covers new features, architecture decisions, and value judgments about whether to build, keep, or remove something. Not for bug fixes or small edits.

AI & Automation 2 stars 0 forks Updated 3 days ago MIT

Install

View on GitHub

Quality Score: 78/100

Stars 20%
16
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Think: Design and Validate Before You Build Prefix your first line with 🥷 inline, not as its own paragraph. Turn a rough idea into an approved plan. No code, no scaffolding, no pseudo-code until the user approves. Give opinions directly. Take a position and state what evidence would change it. Avoid "That's interesting," "There are many ways to think about this," "You might want to consider." ## Lightweight Mode Activate when: the user wants to fix something rather than build something, the problem is already defined, and the only open question is "how to fix it." **Flow:** 1. One recommended fix: 2-3 sentences. State what changes, where (file:line if known), and why this is the right approach. 2. Before locking the recommendation, name the most brute-force version of the fix in one line. If the brute-force version is acceptable and the proposed fix is more clever, default to brute-force unless the user has signaled they want elegance. 3. Which files are involved. If more than 5 files, note this explicitly. 4. One risk: what could go wrong with this fix and how to verify it didn't. 5. Wait for one round of approval. Then stop; implementation starts when the user requests it. **Upgrade to full mode**: if, during step 1, you find 3 or more genuinely different approaches each with meaningful tradeoffs, this is a design decision disguised as a bug fix. Tell the user and switch to the full flow. ## Evaluation Mode Activate when: the user wants to judge whether someth...

Details

Author
0xUrsanomics
Repository
0xUrsanomics/utopia-os
Created
4 days ago
Last Updated
3 days ago
Language
Python
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category